⚡ Built for AI agents & LLM pipelines

YouTube transcripts, one API call away

Pull clean transcripts, search videos and channels, and track new uploads — without scraping, proxies, or breakage. Simple credits, no rate-limit roulette.

Works with ChatGPT Claude MCP Clients Any HTTP stack
500K+
transcripts processed daily
SummarizerBot Verified production user
Processes ~1.2M transcripts/month to power video summaries for its AI assistant.
ResearchDeck Verified production user
Indexes ~400K videos/month across creator channels for semantic search.

Everything your agent needs from YouTube

Seven focused endpoints. Predictable credit pricing. Responses shaped for LLM consumption.

Get Transcripts

1 credit / request

Fetch the full transcript of any public video as clean JSON or plain text, with or without timestamps.

  • Auto-detects available caption languages
  • Timestamps optional — perfect for chunking
  • Video metadata included on request
Read the docs
REQUEST
GET /v1/youtube/transcript?video_url=https://youtu.be/dQw4...
Authorization: Bearer tl_live_xxx
RESPONSE
{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": [
    { "text": "Welcome back to the channel...", "start": 0.0, "duration": 3.2 }
  ]
}

Search YouTube

1 credit / request

Query YouTube for videos, channels, or playlists and get structured results with continuation-token pagination.

  • Filter by result type
  • Stable pagination via continuation tokens
  • Thumbnails, durations, and view counts included
Read the docs
U
Find me recent talks about vector databases and summarize the best one.
A
Searching YouTube for vector database talks…
→ GET /v1/youtube/search?q=vector+databases+talk+2026
→ GET /v1/youtube/transcript?video_url=…
Found 18 results — the standout is a 40-min conference talk. Here's the summary: …

Search Within a Channel

1 credit / request

Scope your search to a single channel — by handle, ID, or URL — to find exactly the videos you need.

  • Accepts @handle, channel ID, or full URL
  • Same clean result shape as global search
  • Paginate through the entire back catalog
Read the docs
REQUEST
GET /v1/youtube/channel/search?channel=@fireship&q=rust
RESPONSE
{
  "results": [
    { "video_id": "5C_HPTJg5ek", "title": "Rust in 100 Seconds" }
  ],
  "continuation": "EpcDEg1..."
}

Browse Channel Videos

1 credit / page

List every upload on a channel, newest first, with full metadata — ideal for building channel-wide indexes.

  • Complete upload history, paginated
  • Consistent ordering for incremental syncs
  • Pairs with transcripts for bulk ingestion
Read the docs
REQUEST
GET /v1/youtube/channel/videos?channel=@veritasium
RESPONSE
{
  "videos": [ /* 30 per page */ ],
  "continuation": "4qmFsgKF..."
}

Track New Uploads

Free

Poll a channel's latest uploads at no credit cost — the cheapest way to trigger downstream workflows.

  • Zero credits — poll as often as you like within rate limits
  • Returns the newest uploads with publish times
  • Diff against your store to detect fresh videos
Read the docs
REQUEST
GET /v1/youtube/channel/latest?channel=@mkbhd
RESPONSE
{
  "latest": [
    { "video_id": "aX3jf9Qw1kE", "published": "2 hours ago" }
  ]
}

Extract Playlists

1 credit / page

Expand any playlist into its full video list — courses, series, and curated collections become ingestible datasets.

  • Handles playlists of any length
  • Position, title, and duration per entry
  • Feed results straight into the transcript endpoint
Read the docs
REQUEST
GET /v1/youtube/playlist/videos?playlist=PLBmc...
RESPONSE
{
  "playlist_id": "PLBmc...",
  "videos": [ /* ordered entries */ ],
  "continuation": null
}

Three ways to plug in

Use plain REST, connect an MCP server to your AI client, or let an agent skill set everything up for you.

⚙️

REST API

A single base URL and Bearer-token auth. Works from any language or runtime in under a minute.

TERMINAL
curl "https://api.transcribelayer.com/v1/youtube/transcript?video_url=..." \
  -H "Authorization: Bearer tl_live_xxx"
🔌

MCP Server

Give Claude, ChatGPT, or any MCP client direct access to every endpoint as native tools.

TERMINAL
claude mcp add transcribelayer \
  -e ABT_API_KEY=tl_live_xxx \
  -- npx @transcribelayer/mcp
🤖

Agent Skill

One command installs a skill that teaches your coding agent when and how to call the API.

TERMINAL
npx skills add transcribelayer/agent-skill

One plan. Every feature.

No tiers to decode — every subscription includes all endpoints. Pay only for the credits you use.

Monthly
$5/month
1,000 credits included · $0.005 per extra credit
  • All 7 endpoints, full access
  • Transcripts in JSON or plain text
  • MCP server & agent skill included
  • Credits roll over 1 month
  • Email support
Start Monthly

Estimate your monthly cost

Drag to your expected volume — most requests cost 1 credit.

10,000 credits / month
1K250K500K750K1M
$50.00
est. monthly total
$0.0050
per credit

Need more than 1M credits/month or custom terms? Talk to us about a custom plan →